SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS

In this paper we present a modified neural network architecture and an algorithm that enables neural networks to learn vectors in accordance to user designed sequences or graph structures. This enables us to use the modified network algorithm to identify, generate or complete specified patterns that...

Full description

Bibliographic Details
Main Authors: Tonimir Kišasondi, Alen Lovrenčić
Format: Article
Language:English
Published: University of Zagreb, Faculty of organization and informatics 2006-06-01
Series:Journal of Information and Organizational Sciences
Online Access:http://jios.foi.hr/index.php/jios/article/view/10